How-ToDevelopersNovember 5, 2026

Hugging Face livestream covers quantization with llama.cpp and vLLM

Read original source →youtube.com

Session titled "Local AI 301: Quantization" walks through shrinking models to run on a laptop, with talks on calibration-based quantization and quantization-aware distillation. Speakers include Merve Noyan, Maxime Labonne, Colin Kealty (bartowski), Aditya Tadimeti and Michael Goin.

People · Merve Noyan, Maxime Labonne, Colin Kealty

2 sources

More stories today

Open the live feed